Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    DOMAIN
    0.80
    ın
    0.70
    ial
    0.69
    interface
    0.69
    તિ
    0.69
    am
    0.67
    rene
    0.66
    ıt
    0.66
    一
    0.66
    ית
    0.65
    POSITIVE LOGITS
     поэтому
    1.02
     кры
    1.00
     другой
    0.94
     начали
    0.93
     непло
    0.89
     быстро
    0.89
    лык
    0.88
     usw
    0.88
     всегда
    0.88
     защиты
    0.88
    Act Density 0.002%

    No Known Activations